{
  "error": {
    "message": "Rate limit exceeded: 300 requests per minute.",
    "type": "rate_limit_error",
    "code": "rate_limit_exceeded"
  }
}

import time
from openai import OpenAI, RateLimitError

client = OpenAI(
    api_key="kr-your-api-key",
    base_url="https://api.k-router.com/v1"
)

def call_with_retry(messages, max_retries=3):
    for attempt in range(max_retries):
        try:
            return client.chat.completions.create(
                model="kr/gpt54",
                messages=messages
            )
        except RateLimitError:
            wait = 2 ** attempt
            print(f"Rate limited. {wait}초 후 재시도...")
            time.sleep(wait)
    raise Exception("최대 재시도 횟수 초과")